Utilizing a Machine Learning Model to Crowdsource Funds for Public Services

1. A method, comprising: providing, by a device and to a user device, task data identifying tasks to be performed; receiving, by the device and from the user device, a selection of a particular task from the tasks to be performed, wherein the particular task is to be performed by a user of the user device; identifying, by the device, one or more cameras associated with a particular task location, wherein the particular task location includes a geographical location where the particular task is to be performed; receiving, by the device and from the user device, data identifying a location of the user device; determining, by the device, that the location of the user device matches the particular task location; receiving, by the device and from the user device, task image data identifying images of the particular task location; accessing, by the device and from the one or more cameras identified as associated with the particular task location, camera data identifying images of the particular task location; processing, by the device, the task image data and the camera data, with a machine learning model, to determine performance data, wherein the machine learning model is trained with historical task image data and historical camera data associated with performance of a plurality of historical tasks to determine predicted performance data, and wherein the processing includes: performing binary recursive partitioning to split the historical task image data and the historical camera data into partitions used to determine outcomes associated with at least one of: an operation that was performed as part of the particular task, a percentage of the particular task that was performed by the user, funding available for the particular task, or funding available to pay the user, and wherein the performance data includes data identifying at least two of: what was performed for the particular task, how much of the particular task was performed by the user, particular funds available for the particular task, or an amount of money to pay the user; and performing, by the device, one or more actions based on the performance data.

2. The method of claim 1 , wherein performing the one or more actions comprises one or more of: providing the amount of money, from the particular funds, to an account associated with the user; or providing, to the user device, data identifying the amount of money provided to the account.

3. The method of claim 1 , wherein performing the one or more actions comprises one or more of: assigning points, based on the amount of money and to be redeemed for money, to a profile associated with the user; posting images of the user and performance of the particular task to a website; providing a community service award to the user based on performance of the particular task; or retraining the machine learning model based on the performance data.

4. The method of claim 1 , further comprising: providing, to a plurality of user devices, the task data identifying the tasks to be performed; receiving, from the plurality of user devices and based on the task data, funding data associated with performance of the tasks, wherein the funding data identifies funds to allocate for performance of the tasks; and receiving, from one or more server devices, the funds based on the funding data.

5. The method of claim 1 , further comprising: receiving user image data identifying the user performing the particular task at the particular task location; and performing facial recognition on the user image data to identify an identity of the user.

6. The method of claim 1 , further comprising one of: training the machine learning model, with the historical task image data and the historical camera data associated with performance of the plurality of historical tasks, to determine the predicted performance data; or receiving the machine learning model from another device, wherein the machine learning model is trained by the other device.

7. The method of claim 1 , further comprising: receiving, from the user device, information indicating particular tasks that the user is willing to perform, wherein providing, to the user device, the task data identifying the tasks to be performed includes: providing, to the user device, the task data identifying the tasks to be performed based on the information indicating the particular tasks that the user is willing to perform.

8. A device, comprising: one or more memories; and one or more processors, communicatively coupled to the one or more memories, configured to: provide, to a user device, task data identifying tasks to be performed; receive, from the user device, a selection of a particular task from the tasks to be performed, wherein the particular task is to be performed by a user of the user device; identify one or more cameras associated with a particular task location, wherein the particular task location includes a geographical location where the particular task is to be performed; receive, from the user device, data identifying a location of the user device; determine that the location of the user device matches the particular task location; receive, from the user device, task image data identifying images of the particular task location; access, from the one or more cameras identified as associated with the particular task location, camera data identifying images of the particular task location; process the task image data and the camera data, with a machine learning model, to determine performance data, wherein the machine learning model is trained with historical task image data and historical camera data associated with performance of a plurality of historical tasks to determine predicted performance data, and wherein the one or more processors, when processing, are configured to: perform binary recursive partitioning to split the historical task image data and the historical camera data into partitions used to determine outcomes associated with at least one of: an operation that was performed as part of the particular task, a percentage of the particular task that was performed by the user, funding available for the particular task, or funding available to pay the user, and wherein the performance data includes data identifying at least two of: what was performed for the particular task, how much of the particular task was performed by the user, particular funds available for the particular task, or an amount of money to pay the user; and perform one or more actions based on the performance data.

9. The device of claim 8 , wherein the one or more processors, when performing the one or more actions, are configured to: provide the amount of money, from the particular funds, to an account associated with the user; or provide, to the user device, data identifying the amount of money provided to the account.

10. The device of claim 8 , wherein the one or more processors, when performing the one or more actions, are configured to: assign points, based on the amount of money and to be redeemed for money, to a profile associated with the user; post images of the user and performance of the particular task to a website; provide a community service award to the user based on performance of the particular task; or retrain the machine learning model based on the performance data.

11. The device of claim 8 , wherein the one or more processors are further configured to: provide, to a plurality of user devices, the task data identifying the tasks to be performed; receive, from the plurality of user devices and based on the task data, funding data associated with performance of the tasks, wherein the funding data identifies funds to allocate for performance of the tasks; and receive, from one or more server devices, the funds based on the funding data.

12. The device of claim 8 , wherein the one or more processors are further configured to: receive user image data identifying the user performing the particular task at the particular task location; and perform facial recognition on the user image data to identify an identity of the user.

13. The device of claim 8 , wherein the one or more processors are further configured to one of: train the machine learning model, with the historical task image data and the historical camera data associated with performance of the plurality of historical tasks, to determine the predicted performance data; or receive the machine learning model from another device, wherein the machine learning model is trained by the other device.

14. The device of claim 8 , wherein the one or more processors are further configured to: receive, from the user device, information indicating particular tasks that the user is willing to perform, wherein the one or more processors, when providing, to the user device, the task data identifying the tasks to be performed, are configured to: provide, to the user device, the task data identifying the tasks to be performed based on the information indicating the particular tasks that the user is willing to perform.

15. A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to: provide, to a user device, task data identifying tasks to be performed; receive, from the user device, a selection of a particular task from the tasks to be performed, wherein the particular task is to be performed by a user of the user device; identify one or more cameras associated with a particular task location, wherein the particular task location includes a geographical location where the particular task is to be performed; receive, from the user device, data identifying a location of the user device; determine that the location of the user device matches the particular task location; receive, from the user device, task image data identifying images of the particular task location; access, from the one or more cameras identified as associated with the particular task location, camera data identifying images of the particular task location; process the task image data and the camera data, with a machine learning model, to determine performance data, wherein the machine learning model is trained with historical task image data and historical camera data associated with performance of a plurality of historical tasks to determine predicted performance data, and wherein the one or more instructions, that cause the one or more processors to process, cause the one or more processors to: perform binary recursive partitioning to split the historical task image data and the historical camera data into partitions used to determine outcomes associated with at least one of: an operation that was performed as part of the particular task, a percentage of the particular task that was performed by the user, funding available for the particular task, or funding available to pay the user, and wherein the performance data includes data identifying at least two of: what was performed for the particular task, how much of the particular task was performed by the user, particular funds available for the particular task, or an amount of money to pay the user; and perform one or more actions based on the performance data.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the device to perform the one or more actions, cause the device to: provide the amount of money, from the particular funds, to an account associated with the user; or provide, to the user device, data identifying the amount of money provided to the account.

17. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the device to perform the one or more actions, cause the device to: assign points, based on the amount of money and to be redeemed for money, to a profile associated with the user; post images of the user and performance of the particular task to a website; provide a community service award to the user based on performance of the particular task; or retrain the machine learning model based on the performance data.

18. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to: provide, to a plurality of user devices, the task data identifying the tasks to be performed; receive, from the plurality of user devices and based on the task data, funding data associated with performance of the tasks, wherein the funding data identifies funds to allocate for performance of the tasks; and receive, from one or more server devices, the funds based on the funding data.

19. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to: receive user image data identifying the user performing the particular task at the particular task location; and perform facial recognition on the user image data to identify an identity of the user.

20. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to: receive, from the user device, information indicating particular tasks that the user is willing to perform, wherein the one or more instructions, that cause the device to provide, to the user device, the task data identifying the tasks to be performed, cause the device to: provide, to the user device, the task data identifying the tasks to be performed based on the information indicating the particular tasks that the user is willing to perform.